ClawHub
Back to skill

Security audit

Finance Office Automation

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only finance office template skill with no executable code, persistence, credential use, or hidden data movement.

Install only if you want general finance-office drafting templates and checklists. Because the trigger terms are broad, invoke it with explicit finance-office context and avoid pasting confidential customer, account, or internal approval data unless your organization permits that use and the data has been minimized or redacted.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger keywords are very broad and include generic terms such as office automation, email, report, approval, and meeting minutes. In an agent ecosystem, this can cause the skill to activate in many ordinary business conversations, exposing unrelated user content to the skill and increasing the chance of inappropriate use in sensitive financial workflows.

Static analysis

No suspicious patterns detected.